All Issue

2024 Vol.57, Issue 11 Preview Page

Research Article

Development of computer vision-based water pipe internal defect quantification technique

Computer vision 기반 상수관로 내부결함 정량화 기법 개발

Ga On Kwona
,
Hui Geun Kwonb
,
Young Hwan Choic*
권 가온a
,
권 희근b
,
최 영환c*
aMaster Degree Student, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
bMaster Degree Student, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
cAssociate Professor, Department of Civil and Infrastructure Engineering, Gyeongsang National University, Jinju, Korea
a경상국립대학교 건설시스템공학과 석사과정
b경상국립대학교 건설시스템공학과 석사과정
c경상국립대학교 건설시스템공학과 부교수
*Corresponding Author
30 November 2024. pp. 835-845
PDF XML Citation
Abstract

Water distribution systems are essential social infrastructure in modern cities. Water pipelines that were intensively built in the 1980s are now aging, causing abnormalities such as vwater leaks and pipe ruptures. To prevent this in advance, direct inspection of the pipeline is used to assess the timing for rehabilitation and replacement, as outlined in the “Detailed Investigation Manual for Water Pipelines (2020).” Although direct evaluation in principle requires excavation and specimen inspection of the pipe, due to spatial and temporal constraints, CCTV inspections in the form of endoscopy are mainly utilized. However, CCTV inspections, being manual and labor- intensive evaluations, make it difficult to expect quantitative and consistent assessments. Hence, this study proposes a method for quantitatively assessing internal defects in water pipelines by using AI-based defect detection and determining the vanishing point in the depth map to measure the size and ratio of the detected defects. In addition, the technique proposed in this study was used to construct a simulated defect inside a ductile iron pipe that was replaced after being determined to be aged, and the actual values ​​were compared with the measured values.

Keywords
Internal defect detection
Internal defect evaluation
Vanishing point
Water distribution system

상수도시스템은 현대 도시에서 필수적인 사회기반시설이다. 1980년대 집중적으로 건설된 상수도 네트워크는 현재 노후화가 진행됨에 따라 누수, 관 파단 등의 비정상사태를 유발하게 된다. 이를 미연에 방지하기 위해 관로 내부를 육안으로 점검하여 갱생 및 교체 시기를 판단하는 ｢상수관망 정밀조사 매뉴얼(2020)｣의 직접평가는 원칙적으로 관체 굴착 및 시편조사를 수행하여야 하나 공간적·시간적 제약에 의해 내시경 형태의 CCTV 조사가 주로 활용되고 있다. 하지만 CCTV 조사는 수동적인 인력기반의 평가로 정량적이고 일관적인 평가를 기대하기 어렵다. 따라서, 본 연구에서는 상수도관로의 내부결함을 정량적으로 평가하기 위해 AI기반 내부결함 탐지와 탐지한 결함의 크기를 결정하기 위한 소실점을 Depth map에서 검출하여 내부결함의 크기 및 비율을 측정하는 기법을 제안한다. 그리고 본 연구에서 제안하는 기법을 노후추정으로 판별되어 교체된 덕타일 주철관 내부에 모의결함을 구성하여 실제값과 측정값을 비교하였다.

키워드
내부결함 탐지
내부결함 평가
상수도 시스템
소실점
References
1

Bradski, G., and Kaehler, A. (2008). Learning OpenCV: Computer vision with the OpenCV library. O'Reilly Media, Inc., Sebastopol, Sonoma County, CA, U.S.

2

Canny, J.F. (1983). Finding edges and lines in images, Tech. Report, 720, MIT Artificial Intelligence Laboratory, Massachusetts Institute of Technology, Boston, MA, U.S., pp. 70-85.

3

Chen, K., Hu, H., Chen, C., Chen, L., and He, C. (2018). "An intelligent sewer defect detection method based on convolutional neural network." In 2018 IEEE International Conference on Information and Automation (ICIA), IEEE, Wuyi Mountain, Fujian, China, pp. 1301-1306.

10.1109/ICInfA.2018.8812445
4

Girshick, R. (2015). "Fast r-cnn." In Proceedings of the IEEE International Conference on Computer Vision, Cambridge, MA, U.S., pp. 1440-1448.

10.1109/ICCV.2015.169
5

Girshick, R., Donahue, J., Darrell, T., and Malik, J. (2014). "Rich feature hierarchies for accurate object detection and semantic segmentation." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, U.S., pp. 580-587.

10.1109/CVPR.2014.81
6

Kirkpatrick, S., Gelatt Jr, C.D., and Vecchi, M.P. (1983). "Optimization by simulated annealing." Science, Vol. 220, No. 4598, pp. 671-680.

10.1126/science.220.4598.67117813860
7

Laven, K., Jones, C., Larsen, M., and Payton, R. (2008). "Inline CCTV inspections of in-service pressurized water mains." in Pipelines 2008, American Society of Civil Engineers, Reston, VA, U.S., pp. 1-10.

10.1061/40994(321)108
8

Liu, Z., and Kleiner, Y. (2013). "State of the art review of inspection technologies for condition assessment of water pipes." Measurement, Vol. 46, No. 1, pp. 1-15.

10.1016/j.measurement.2012.05.032
9

Ministry of Environment (ME) (2020). Detailed investigation manual for water pipelines.

10

Ministry of Environment (ME) (2022). Water supply statistics.

11

Mirats Tur, J.M., and Garthwaite, W. (2010). "Robotic devices for water main in‐pipe inspection: A survey." Journal of Field Robotics, Vol. 27, No. 4, pp. 491-508.

10.1002/rob.20347
12

Moradi, S., Zayed, T., and Golkhoo, F. (2019). "Review on computer aided sewer pipeline defect detection and condition assessment." Infrastructures, Vol. 4, No. 1, p. 10.

10.3390/infrastructures4010010
13

Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., El-Nouby, A., et al. (2023). "Dinov2: Learning robust visual features without supervision." arXiv preprint arXiv:2304.07193.

14

Rayhana, R., Yun, H., Liu, Z., and Kong, X. (2023). "Automated defect-detection system for water pipelines based on CCTV inspection videos of autonomous robotic platforms." IEEE/ASME Transactions on Mechatronics, Vol. 29, No. 3, pp. 2021-2031.

10.1109/TMECH.2023.3307594
15

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). "You only look once: Unified, real-time object detection." In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, U.S., pp. 779-788.

10.1109/CVPR.2016.91
16

Ren, S., He, K., Girshick, R., and Sun, J. (2016). "Faster R-CNN: Towards real-time object detection with region proposal networks." IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 39, No. 6, pp. 1137-1149.

10.1109/TPAMI.2016.257703127295650
17

Su, T.C., and Yang, M.D. (2014). "Application of morphological segmentation to leaking defect detection in sewer pipelines." Sensors, Vol. 14, No. 5, pp. 8686-8704.

10.3390/s14050868624841247PMC4063020
18

Terven, J., Córdova-Esparza, D.M., and Romero-González, J.A. (2023). "A comprehensive review of yolo architectures in computer vision: From yolov1 to yolov8 and yolo-nas." Machine Learning and Knowledge Extraction, Vol. 5, No. 4, pp. 1680-1716.

10.3390/make5040083
19

Ultralytics (2023). YOLOv8, accessed 7 November 2024, <https://docs.ultralytics.com/ko/models/yolov8/>

20

Yang, M.D., and Su, T.C. (2009). "Segmenting ideal morphologies of sewer pipe defects on CCTV images for automated diagnosis." Expert Systems with Applications, Vol. 36, No. 2, pp. 3562-3573.

10.1016/j.eswa.2008.02.006
21

Yin, X., Ma, T., Bouferguene, A., and Al-Hussein, M. (2021). "Automation for sewer pipe assessment: CCTV video interpretation algorithm and sewer pipe video assessment (SPVA) system development." Automation in Construction, Vol. 125, 103622.

10.1016/j.autcon.2021.103622
Information
  • Publisher :KOREA WATER RESOURECES ASSOCIATION
  • Publisher(Ko) :한국수자원학회
  • Journal Title :Journal of Korea Water Resources Association
  • Journal Title(Ko) :한국수자원학회 논문집
  • Volume : 57
  • No :11
  • Pages :835-845
  • Received Date : 2024-09-06
  • Revised Date : 2024-10-08
  • Accepted Date : 2024-10-11
  • DOI :https://doi.org/10.3741/JKWRA.2024.57.11.835
Journal Informaiton Journal of Korea Water Resources Association Journal of Korea Water Resources Association
Online Submission
Archives
  • scopus
  • KCI-수자원
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close